用于诗人的 tensorflow：“名称‘import/Mul’指的是不在图中的操作。”

Question

© 尝试使用 tensorflow 图像再训练。 https://www.tensorflow.org/tutorials/image_retraining

这样训练，没关系：

D:\dev\Anaconda\python D:/dev/detect_objects/tensorflow-master/tensorflow/examples/image_retraining/retrain.py --image_dir D:/dev/detect_objects/flower_photos --bottleneck_dir D:/dev/detect_objects/tensorflow-master/retrain/bottleneck --architecture mobilenet_0.25_128 --output_graph D:/dev/detect_objects/tensorflow-master/retrain/output_graph/output.pb --output_labels D:/dev/detect_objects/tensorflow-master/retrain/output_labels/labels.txt --saved_model_dir D:/dev/detect_objects/tensorflow-master/retrain/saved_model_dir --how_many_training_steps 100

当预测新图像时：

D:\dev\Anaconda\python D:/dev/detect_objects/tensorflow-master/tensorflow/examples/label_image/label_image.py --graph=D:/dev/detect_objects/tensorflow-master/retrain/output_graph/output.pb  --labels=D:/dev/detect_objects/tensorflow-master/retrain/output_labels/labels.txt --image=D:/dev/detect_objects/flower_photos/daisy/21652746_cc379e0eea_m.jpg

报错

KeyError: "The name 'import/Mul' refers to an Operation not in the graph."

label_image.py 内容：

  input_height = 299
  input_width = 299
  input_mean = 0
  input_std = 255
  #input_layer = "input"
  #output_layer = "InceptionV3/Predictions/Reshape_1"

  input_layer = "Mul"
  output_layer = "final_result"

这里有什么问题？

Answer 1

如果图中没有名为“import/Mul”的节点并且我们不知道 图表是什么或它是如何产生的，几乎没有机会 任何人都能猜出正确的答案。

您可以尝试使用graph.get_operations() 打印图表的操作列表并尝试找到合适的节点（尝试打印的第一个节点）

Answer 2

改变这个：

  input_height = 299
  input_width = 299
  input_mean = 0
  input_std = 255
  #input_layer = "input"
  #output_layer = "InceptionV3/Predictions/Reshape_1"

  input_layer = "Mul"
  output_layer = "final_result"

到这里：

   input_height = 128
   input_width = 128
   input_mean = 0
   input_std = 128
   input_layer = "input"
   output_layer = "final_result"